agentmods.dev

oracle AGENTS.md

Project instructions describe how to use Oracle, a tool that lets developers ask another AI model for help with code and files. They also document test settings, browser runs, waiting behavior, saved sessions, and command-line output.

In plain words
What is it for?
Use them when you are stuck on a coding problem, need Oracle to inspect files, or are running Oracle-related tests and command-line tasks.
Why use it?
They give the coding agent project-specific rules for asking Oracle and running its slower tests. This reduces confusion about which model, account, test mode, or session to use.

Instructions file for CodexOpenCode

3.8k +81 2d ago A scan 1,193 tokens original MIT
▶ The Codex Oracle, A Deck That Doesn’t Give Answers! The Hermit’s Cave · about steipete/oracle · on YouTube →
View the source file steipete/oracle
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/steipete/oracle/agents-md
Clone the repo
git clone --depth 1 https://github.com/steipete/oracle

Made for: Codex, OpenCode.

Per session 1,193 This file is loaded in full into every session.
When invoked 1,193 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.01193 $0.01193
Opus 5 $0.00596 $0.00596
Sonnet 5 $0.00239 $0.00239
Haiku 4.5 $0.00119 $0.00119

Measured 2d ago against content hash ca4085936eb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

oracle AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.MD

Oracle-specific notes:

  • ChatGPT project URLs: [email protected] -> https://chatgpt.com/g/g-p-691edc9fec088191b553a35093da1ea8-oracle/project; [email protected] -> https://chatgpt.com/g/g-p-69505ed97e3081918a275477a647a682/project. Prefer studpete URL if steipete project not found.
  • Pro browser runs: allow up to 10 minutes; never click "Answer now"; keep at least 1–2 Pro live tests (reattach must stay Pro); move other tests to faster models where safe.
  • Live smoke tests: OpenAI live tests are opt-in. Run ORACLE_LIVE_TEST=1 pnpm vitest run tests/live/openai-live.test.ts with a real OPENAI_API_KEY when you need the background path; gpt-5-pro can take ~10 minutes.
  • Wait defaults: gpt-5-pro API runs detach by default; use --wait to stay attached. gpt-5.1 and browser runs block by default; every run prints oracle session <id> for reattach.
  • Session storage: Oracle stores session data under ~/.oracle; delete it if you need a clean slate.
  • CLI output: the first line of any top-level CLI start banner should use the oracle emoji, e.g. 🧿 oracle (<version>) ...; keep it only for the initial command headline. Exception: the TUI exit message also keeps the emoji.
  • Model access note (2025-11-23): gpt-5.1-pro and grok-4.1 are not yet available on Peter’s keys; live tests that require them will fail until access is granted.
  • Oracle CLI on Node 25: if pnpm dlx @steipete/oracle --help fails with a missing node_sqlite3.node, rebuild sqlite3 in the pnpm dlx cache using system Python: PYTHON=/usr/bin/python3 /Users/steipete/Projects/oracle/runner npx node-gyp rebuild from the sqlite3 package dir printed in the error, then rerun the command.
  • Before a release, skim manual smokes in docs/manual-tests.md and rerun any that cover your change surface (especially browser/serve paths).
  • If browser smokes echo the prompt (Instant), rerun with --browser-keep-browser --verbose in tmux, then inspect DOM with pnpm tsx scripts/browser-tools.ts eval ... to confirm assistant turns exist; we fixed a case by refreshing assistant snapshots post-send.
  • Browser “Pro thinking” gate: never click/auto-click ChatGPT’s “Answer now” button. Treat it as a placeholder and wait 10m–1h for the real assistant response (auto-clicking skips long thinking and changes behavior).
  • Browser smokes should preserve Markdown (lists, fences); if output looks flattened or echoed, inspect the captured assistant turn via browser-tools.ts eval before shipping.
  • Working on Windows? Read and update docs/windows-work.md before you start.
  • Sparkle signing key lives at /Users/steipete/Library/CloudStorage/Dropbox/Backup/Sparkle; set SPARKLE_PRIVATE_KEY_FILE to that path when notarizing the notifier.
  • Browser cookie sync + Node 25: if browser runs fail with “Failed to load keytar… Cannot find module '../build/Release/keytar.node'” and no cookies are applied, rebuild keytar in the pnpm dlx cache: run PYTHON=/usr/bin/python3 /Users/steipete/Projects/oracle/runner npx node-gyp rebuild inside the keytar directory printed in the error, then rerun the oracle command.
  • npm publish OTP: prepare/tag/release first, then run npm publish ... and stop at Enter OTP:; ask user for the OTP and continue (ok to handle OTP in chat).

Browser-mode debug notes (ChatGPT URL override)

  • When a ChatGPT folder/workspace URL is set, Cloudflare can block automation even after cookie sync. Use --browser-keep-browser to leave Chrome open, solve the interstitial manually, then rerun.
  • If a run stalls/looks finished but CLI didn’t stream output, check the latest session (oracle status) and open it (oracle session <id> --render) to confirm completion.
  • Active Chrome port/pid live in session metadata (~/.oracle/sessions/<id>/meta.json). Connect with npx tsx scripts/browser-tools.ts eval --port <port> "({ href: window.location.href, ready: document.readyState })" to inspect the page.
  • To debug with agent-tools, launch Chrome via an Oracle browser run (cookies copied) and keep it open (--browser-keep-browser). Then use ~/Projects/agent-scripts/bin/browser-tools ... --port <port> with the port from ~/.oracle/sessions/<id>/meta.json. Avoid starting a fresh browser-tools Chrome when you need the synced cookies.
  • Double-hop nav is implemented (root then target URL), but Cloudflare may still need manual clearance or inline cookies.
  • After finishing a feature, ask whether it matters to end users; if yes, update the changelog. Read the top ~100 lines first and group related edits into one entry instead of scattering multiple bullets.
  • Beta publishing: when asked to ship a beta to npm, bump the version with a beta suffix (e.g., 0.4.4-beta.1) before publishing; npm will not let you overwrite an existing beta tag without a new version.

Read the full file on GitHub · 31 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 31 lines · 1,193 tokens per session scan A ca4085936eb8

Subscribe to this mod's changes

oracle AGENTS.md is an instructions file published in the GitHub repository steipete/oracle (3,838 stars, last pushed 2d ago), licensed MIT. It adds 1,193 tokens to every session, about $0.0060 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

agentsaianthropicgemini-progpt-5-proopenai
Related

Other instructions, from other repositories

openai-agents-python AGENTS.md

AGENTS.md instructions for openai/openai-agents-python, covering contributor guide, policies & mandatory rules, mandatory skill usage, work status reporting and git worktree and branch safety.

openai/openai-agents-python · 8,006 tokens

AI-Gateway AGENTS.md

Instructions for Azure-Samples/AI-Gateway, covering agents.md, directory structure, labs/, modules/ and shared/.

Azure-Samples/AI-Gateway · 1,322 tokens

opengeni AGENTS.md

Instructions for Cloudgeni-ai/opengeni, covering agent / automation notes (opengeni), full local stack, architecture notes, pull-request delivery across moving main and keeping these notes current.

Cloudgeni-ai/opengeni · 21,782 tokens

Assistant CLAUDE.md

Instructions for bearlike/Assistant, covering agents guide — mewbo, mandatory: hydrate before touching files, what mewbo is, monorepo layering — read before adding a module and engineering principles.

bearlike/Assistant · 6,737 tokens

axonhub AGENTS.md

AGENTS.md instructions for looplj/axonhub, covering agents.md, global rules, configuration, project overview and technology stack.

looplj/axonhub · 1,168 tokens

axonhub CLAUDE.md

Claude Code instructions for looplj/axonhub: @AGENTS.md read and follow its instructions.

looplj/axonhub · 10 tokens